Alternatives and similar repositories for emergent-misalignment:

Users that are interested in emergent-misalignment are comparing it to the libraries listed below

• METR / task-standard
  METR Task Standard
  ☆146Updated 2 months ago
• UKGovernmentBEIS / inspect_evals
  Collection of evals for Inspect AI
  ☆115Updated this week
• METR / vivaria
  Vivaria is METR's tool for running evaluations and conducting agent elicitation research.
  ☆90Updated this week
• andyrdt / refusal_direction
  Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".
  ☆208Updated 6 months ago
• GraySwanAI / circuit-breakers
  Improving Alignment and Robustness with Circuit Breakers
  ☆197Updated 7 months ago
• TransluceAI / observatory
  A toolkit for describing model features and intervening on those features to steer behavior.
  ☆178Updated 5 months ago
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆95Updated 2 months ago
• goodfire-ai / r1-interpretability
  Open source interpretability artefacts for R1.
  ☆82Updated this week
• google-deepmind / mishax
  ☆128Updated 3 weeks ago
• LeonGuertler / TextArena
  A Collection of Competitive Text-Based Games for Language Model Evaluation and Reinforcement Learning
  ☆139Updated this week
• anthropics / sleeper-agents-paper
  Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".
  ☆102Updated last year
• METR / public-tasks
  ☆89Updated last month
• ConsequentAI / fneval
  Functional Benchmarks and the Reasoning Gap
  ☆85Updated 6 months ago
• EleutherAI / delphi
  Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …
  ☆169Updated this week
• google-deepmind / dangerous-capability-evaluations
  ☆54Updated 7 months ago
• stanfordnlp / axbench
  Stanford NLP Python library for benchmarking the utility of LLM interpretability methods
  ☆70Updated 3 weeks ago
• haizelabs / dspy-redteam
  Red-Teaming Language Models with DSPy
  ☆183Updated 2 months ago
• haizelabs / verdict
  Verdict is a library for scaling judge-time compute.
  ☆199Updated last week
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆197Updated 4 months ago
• princeton-pli / hal-harness
  ☆64Updated this week
• centerforaisafety / wmdp
  WMDP is a LLM proxy benchmark for hazardous knowledge in bio, cyber, and chemical security. We also release code for RMU, an unlearning m…
  ☆111Updated last year
• hijohnnylin / neuronpedia
  open source interpretability platform 🧠
  ☆95Updated this week
• OSU-NLP-Group / GrokkedTransformer
  Code for NeurIPS'24 paper 'Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization'
  ☆187Updated 4 months ago
• jonhue / activeft
  PyTorch library for Active Fine-Tuning
  ☆64Updated 2 months ago
• haizelabs / Awesome-LLM-Judges
  ⚖️ Awesome LLM Judges ⚖️
  ☆93Updated 2 months ago
• AsaCooperStickland / situational-awareness-evals
  Measuring the situational awareness of language models
  ☆34Updated last year
• anthropics / attribution-graphs-frontend
  https://transformer-circuits.pub/2025/attribution-graphs/methods.html
  ☆42Updated 3 weeks ago
• nrimsky / LM-exp
  LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces
  ☆91Updated last year
• kanishkg / stream-of-search
  Repository for the paper Stream of Search: Learning to Search in Language
  ☆145Updated 2 months ago
• jerber / lang-jepa
  ☆108Updated 4 months ago